VegaLytics Health

1. Translation and Standardization
2. Data Quality Engine
3. Common Data Model
4. Reference Data Sets
5. Data Warehouse

Health Systems and Health Plans are experiencing a deluge of data. Rapid advancements in social media, data acquisition technologies, digital imaging devices, and wearables are all dumping massive amounts of diverse data into the hands of health plans. This adds to the already-complex network of multiple providers with different IT systems

VegaLytics is designed to ingest any type of Health or Social data. It has prebuilt adapters to ingest EDI, xls, csv, images, IoT, voice, video into a single system.

Translation and Standardization:

A Healthcare eco system produces varied types and formats of data which can be challenging to translate and extract insights for the right context. Additionally, along with mergers and acquisitions, most Health Systems are challenged further wrangling additional sources and perform activities which includes, but is not limited to, data standardization and interoperability, across thousands of cases and providers.

VegaLytics Health has a UI based data translation engine to convert structured data into a common data model. The data translation engine comprises of a set of tools for EDI conversion, xls, csv, direct ingestion of SQL, IoT, Voice, Image and Video into the storage location. The platform requires no coding, only configuration. This greatly reduces the time needed to go live.

Data Quality Engine:

VegaLytics Health Data Quality Engine has prebuilt business rules covering Demographic, Claims, Eligibility information helping Health systems to jumpstart their Data Quality Management (DQM) initiative. It is designed to help run your growing business efficiently by onboarding new customers data smoothly. This ensures all your client’s data is processed and mapped correctly – thereby detecting any early claim leakages. Engine is designed to be scalable, flexible that can integrate with any of client’s partners and can work with any type of data.

The pre-built rules are classified under three categories:

• Data Cleansing Rules: Validates data structures and formats against definitions in the common data model. For example, Social Security Number or Zip codes having alphabets.
• Data Domain Rules: Validates data rules for defined health data domains and values. Examples: Member is missing coverage dates, Date ranges for coverage are invalid, etc.
• Business Logic Rules: Validates Business rules on Domains or cross-domains. For example: claim date outside benefit coverage, Payments matching issues with claims, etc. The cleansed data is fed into the modern data warehouse or can be served back to the health system for further analysis.